© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60552
    Prev
    Next
    INDEX
    Explanations

    words from multilingual contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Outlet
    0.39
    mah
    0.38
    =":
    0.36
     production
    0.36
     Production
    0.35
     Positions
    0.35
     positions
    0.35
     Things
    0.35
     Photographs
    0.35
    GeneratedValue
    0.35
    POSITIVE LOGITS
    샌
    0.48
    Demon
    0.42
     ചെറിയ
    0.39
     πέ
    0.39
    ومي
    0.38
    կ
    0.38
     작은
    0.37
    לך
    0.37
     gere
    0.37
    證明
    0.37
    Activations Density 8.076%

    No Known Activations